mcpbeat Sign in

RCLL MCP Server

local only

RCLL runs on your own machine — the client starts it, so there is no endpoint to ping. 22 installs a week from npm. Last commit 28 Aug 2026.

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

Installs per day peak 304 · avg 19 · -41% w/w
a month agotoday
22
Installs / week
npm · fleet-memory-mcp
0
Stars
0 open issues
28 Aug 2026
Last commit
2 releases in 90 days
MIT
License
Python

What the code does

We read the source, 5 d ago · rules 995398eba69f

In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Runs an external command hindsight-all-npm/src/server.ts:105
    const child = spawn(cmd, args, { stdio: 'pipe' });
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
Secret passed into the image build docker/standalone/Dockerfile:242
ENV TOKENIZERS_PARALLELISM=false

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Nothing serious here today

Today is the operative word: we check RCLL every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add fleet-memory -- npx -y fleet-memory-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "fleet-memory": {
      "command": "npx",
      "args": [
        "-y",
        "fleet-memory-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.fleet-memory]
command = "npx"
args = ["-y", "fleet-memory-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "fleet-memory": {
      "command": "npx",
      "args": [
        "-y",
        "fleet-memory-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "fleet-memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "fleet-memory-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: FLEET_URL (Base URL of the fleet-memory backend (self-hosted). Defaults to http://127.0.0.1:5100. The pre-rebrand name HINDSIGHT_URL is still read as a fallback), FLEET_BANK (Default memory bank ID for retain/recall. The pre-rebrand variable MEMPALACE_BANK is still read as a fallback. Migrating from hindsight-mempalace-mcp? Set this to mempalace-main to keep reading your existing bank; see mcp-server/README.md).

Alternatives to RCLL

same job, measured the same way
Recall
by j4ckxyz

Private, encrypted memory about you, shared by all your AI agents. Self-hosted; runs on a Pi.

local only
Agentics
by agenticstechnologies

Shared memory for AI agents, with a receipt for every write. Hosted MCP at agentics.you/mcp.

answering
Mnemoverse Memory
by mnemoverse

Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp

1 098 installs/wk answering
Threadctx MCP
by threadctx-dev

Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.

33 installs/wk local only
Evc Mesh MCP
by entire-vc

Tasks, comments, shared memory and handoffs for teams of people and AI agents, over MCP.

answering
Recall — persistent memory for agents
by workers-notdown-app-recall

Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.

5 tools answering
Pindoc
by var-gg

Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.

local only
Repo Memory
by yubinkim444

Shared, git-tracked working memory for AI agents on the same codebase.

196 installs/wk local only

RCLL — questions

Answers built from our own checks of this server.

Why is there no uptime for RCLL?
RCLL runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package fleet-memory-mcp was installed 22 times last week.
How do I connect RCLL?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls fleet-memory-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use RCLL?
The npm package fleet-memory-mcp was installed 22 times in the last week. Week over week that is -41%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is RCLL open source?
Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.